---
title: "Martin Schweiger (@marts) | Hashnode"
description: "AI dev + engineer. Read the latest articles by Martin Schweiger on Hashnode."
url: "https://hashnode.com/@marts"
---

@marts

# Martin Schweiger

@marts · New York City, USA · Joined March 2026

AI dev + engineer

### [How to Build an AI Scribe for Therapy Progress Notes](https://voiceaitrendsandtopics.hashnode.dev/how-to-build-an-ai-scribe-for-therapy-progress-notes?utm_source=hashnode&utm_medium=feed)

Ask any therapist where their evenings go and you'll hear the same answer: notes. The session ends, the next client is already in the waiting room, and the progress note gets pushed to a stack that ge

11 min read · [voiceaitrendsandtopics.hashnode.dev](https://voiceaitrendsandtopics.hashnode.dev/how-to-build-an-ai-scribe-for-therapy-progress-notes?utm_source=hashnode&utm_medium=feed)

[Aug 5](https://hashnode.com/posts/how-to-build-an-ai-scribe-for-therapy-progress-notes/6a7335345b587923e6b3bae9)

### [How to Build Real-Time Agent Assist on Streaming STT](https://voiceaitrendsandtopics.hashnode.dev/how-to-build-real-time-agent-assist-on-streaming-stt?utm_source=hashnode&utm_medium=feed)

Real-time agent assist is one of those features that sounds like magic and turns out to be plumbing. The agent is on a call, and as the customer talks, the screen quietly surfaces the right answer, th

10 min read · [voiceaitrendsandtopics.hashnode.dev](https://voiceaitrendsandtopics.hashnode.dev/how-to-build-real-time-agent-assist-on-streaming-stt?utm_source=hashnode&utm_medium=feed)

[Aug 5](https://hashnode.com/posts/how-to-build-real-time-agent-assist-on-streaming-stt/6a733501a0aeed7516674aed)

### [Speech-to-Text API Fundamentals: Auth, Polling & JSON](https://voiceaitrendsandtopics.hashnode.dev/speech-to-text-api-fundamentals-auth-polling-json?utm_source=hashnode&utm_medium=feed)

Every integration with a speech-to-text API comes down to three questions. How do I authenticate? How do I get results out of an async job? And what does the response actually contain? Get those right

11 min read · [voiceaitrendsandtopics.hashnode.dev](https://voiceaitrendsandtopics.hashnode.dev/speech-to-text-api-fundamentals-auth-polling-json?utm_source=hashnode&utm_medium=feed)

[Jul 22](https://hashnode.com/posts/speech-to-text-api-fundamentals-auth-polling-json/6a60db09625bb17c33d34904)

### [Fast ASR for Voice Agents: Bring Your Own Turn Detection](https://voiceaitrendsandtopics.hashnode.dev/fast-asr-for-voice-agents-bring-your-own-turn-detection?utm_source=hashnode&utm_medium=feed)

There's a school of voice-agent development that treats turn detection as something you buy, not something you build. Pick a streaming STT provider, let its end-of-turn logic decide when the user is d

8 min read · [voiceaitrendsandtopics.hashnode.dev](https://voiceaitrendsandtopics.hashnode.dev/fast-asr-for-voice-agents-bring-your-own-turn-detection?utm_source=hashnode&utm_medium=feed)

[Jul 15](https://hashnode.com/posts/fast-asr-for-voice-agents-bring-your-own-turn-detection/6a57ad6b114da622f7681c24)

### [Time to First Token: The Voice Agent Latency Metric](https://voiceaitrendsandtopics.hashnode.dev/time-to-first-token-the-voice-agent-latency-metric?utm_source=hashnode&utm_medium=feed)

Ask an STT vendor how fast they are and you'll get a word error rate and an average latency number. Both are real. Neither tells you whether a conversation with your voice agent will feel alive or fee

10 min read · [voiceaitrendsandtopics.hashnode.dev](https://voiceaitrendsandtopics.hashnode.dev/time-to-first-token-the-voice-agent-latency-metric?utm_source=hashnode&utm_medium=feed)

[Jul 15](https://hashnode.com/posts/time-to-first-token-the-voice-agent-latency-metric/6a57ad1ba04951035e5ee401)
